nemoclaw-maintainer-cross-issue-sweep

Scan open issues to find issues that a PR can also fix or conflict with. Report each relationship with file and line evidence. Use this skill during PR review to find related fixes and risks.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a lean, highly actionable workflow with executable scripts and clear sequencing. The main defect is progressive disclosure: most referenced reference files do not exist in the bundle, so the detailed rules the workflow relies on cannot actually be navigated to.

Suggestions

Ship the missing reference files (repo-policy.md, checks/fingerprint-extraction.md, checks/relationship-judgment.md, templates/report.md, validation/backtest.md, relationship-rules.md) or inline the essential rules they were meant to hold.

Add an explicit validate-and-retry feedback loop (e.g., re-classify low-confidence candidates or re-run search with adjusted caps when too few candidates survive the filter) to push workflow clarity to 5.

Confirm the referenced paths match the bundle layout exactly so links resolve.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — terse steps, no explanation of concepts Claude already knows, and every section (checklist, scripts, references, limits) earns its place.	5 / 5
Actionability	It provides copy-paste-ready commands backed by real scripts ("scripts/extract-fingerprint.sh <pr-number>", "scripts/search-candidate-issues.sh <fingerprint-json>", "scripts/render-report.py < classifications.json") plus concrete classification and filter rules.	5 / 5
Workflow Clarity	A clear six-step sequence with an explicit checklist and validation gates (evidence required per candidate, Step 5 filter drops UNRELATED/low-confidence), but it lacks an explicit error-recovery feedback loop, so it sits at the clear-sequence-with-minor-gaps anchor rather than 5.	4 / 5
Progressive Disclosure	Structure and signaling are good (one-level-deep references, per-file one-line descriptions, a "Scripts (execute, do not read)" section), but six referenced files (repo-policy.md, checks/fingerprint-extraction.md, checks/relationship-judgment.md, templates/report.md, validation/backtest.md, relationship-rules.md) are absent from the bundle, so navigation to the detail the workflow depends on is broken.	3 / 5
	Total	17 / 20 Passed

Description

82%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise, third-person, and answers both what and when with a concrete trigger. Trigger-term coverage is good but could add synonyms like "regression"; specificity is solid but lists only two core actions.

Suggestions

Add one or two more concrete actions (e.g., 'classify each candidate as adjacent-fix or conflict') to lift specificity beyond two actions.

Include natural synonyms such as 'regression' or 'linked issue' to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions — "Scan open issues to find issues that a PR can also fix or conflict with" and "Report each relationship with file and line evidence" — but stops at two actions rather than comprehensive coverage, matching the 1-2 concrete actions anchor.	3 / 5
Completeness	It clearly answers what ("Scan open issues ... Report each relationship with file and line evidence") and explicitly when ("Use this skill during PR review to find related fixes and risks") with a concrete trigger phrase.	5 / 5
Trigger Term Quality	Includes natural maintainer phrases such as "PR review", "related fixes", "risks", "open issues", and "conflict", giving good keyword coverage, though common synonyms like "regression" or "linked issue" are absent.	4 / 5
Distinctiveness Conflict Risk	The cross-issue PR-review niche ("issues that a PR can also fix or conflict with") is a distinct trigger set with minimal overlap risk against general PR-review skills.	5 / 5
	Total	17 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 6 missing	Warning

	Total	14 / 16 Passed

Repository: NVIDIA/NemoClaw
Path: .agents/skills/nemoclaw-maintainer-cross-issue-sweep/SKILL.md
Commit: e987b00

Reviewed: about 3 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.